Corusconsulting is looking for Lead / AI Architect – Agentic AI
Job Summary
We are seeking an experienced AI Lead / AI Architect specializing in Agentic AI and Generative AI to design, develop, and implement scalable, intelligent, and autonomous AI solutions.
The ideal candidate will have strong expertise in Large Language Models (LLMs), multi-agent architectures, Retrieval-Augmented Generation (RAG), AI orchestration frameworks, and enterprise AI integrations.
This role will be responsible for defining AI architecture, leading technical implementation, integrating AI agents with enterprise applications, and ensuring the scalability, security, reliability, and responsible use of AI-powered solutions.
Key Responsibilities
1. Agentic AI Architecture
· Design and implement agentic AI architectures capable of planning, reasoning, tool usage, and executing complex workflows.
· Develop single-agent and multi-agent systems for enterprise business applications.
· Architect AI orchestration, agent communication, memory management, and workflow automation.
· Design human-in-the-loop mechanisms and approval workflows for sensitive operations.
2. Generative AI & LLM Development
· Lead the development of LLM-powered enterprise applications.
· Implement RAG architectures, semantic search, embeddings, and vector databases.
· Design and optimize prompts, tool calling, structured outputs, and agent workflows.
· Evaluate and integrate commercial and open-source LLMs.
3. Technical Leadership & Solution Design
· Define enterprise AI architecture, technical standards, and implementation strategies.
· Lead AI developers, ML engineers, and cross-functional technical teams.
· Conduct architectural reviews, code reviews, and technical mentoring.
· Translate business requirements into scalable AI solutions.
· Build proof-of-concepts (POCs), prototypes, and production-ready AI applications.
4. Enterprise AI Integration
· Integrate AI agents with enterprise applications, databases, APIs, and business workflows.
· Build API-driven architectures using Python, FastAPI, and microservices.
· Design secure integrations with internal and third-party systems.
· Implement event-driven and workflow-based AI automation.
5. AI Deployment, Monitoring & Governance
· Deploy scalable AI applications on AWS, Azure, or Google Cloud.
· Establish evaluation, monitoring, observability, and performance optimization practices.
· Implement guardrails, authentication, access controls, and data privacy protections.
· Optimize LLM latency, token consumption, infrastructure cost, and response quality.
· Implement testing and evaluation frameworks to measure agent performance, task completion, and reliability.
Required Technical Skills
Category | Mandatory Skills |
Agentic AI | Agent architectures, tool calling, orchestration, multi-agent workflows |
GenAI & LLMs | LLMs, prompt engineering, RAG, embeddings |
AI Frameworks | Hands-on experience with LangGraph, AutoGen, CrewAI, or equivalent |
Programming | Strong Python development experience |
Backend & Integration | REST APIs, FastAPI, microservices, enterprise integrations |
Vector Databases | Pinecone, Weaviate, Milvus, FAISS, or equivalent |
Cloud | AWS, Azure, or Google Cloud Platform |
AI Architecture | Solution design, distributed systems, scalability, security |
Deployment | Docker, CI/CD, production AI application deployment |
Leadership | Technical leadership, architecture reviews, stakeholder management |
AI Evaluation | LLM evaluation, agent testing, monitoring, guardrails |
Preferred / Nice-to-Have Skills
· Experience with Model Context Protocol (MCP) and agent interoperability.
· Experience with Azure AI Foundry, Amazon Bedrock, or Google Vertex AI.
· Knowledge of Kubernetes and MLOps/LLMOps practices.
· Experience with model fine-tuning, LoRA, and PEFT.
· Familiarity with knowledge graphs and Graph RAG.
· Experience implementing AI governance and responsible AI frameworks.
· Experience with OpenTelemetry, LangSmith, Langfuse, or comparable observability tools.
· Experience delivering enterprise AI transformation programs.
· Knowledge of AI security, prompt injection mitigation, and agent access controls.
Qualifications
· Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Engineering, or related field.
· Strong experience in enterprise software architecture and AI solution development.
· Proven hands-on experience building and deploying LLM-powered or agentic AI applications.
· Demonstrated ability to lead technical teams and drive AI implementations from concept to production.
· Strong problem-solving, communication, and stakeholder-management skills.
